text-generation

Boogu-Image

Python

72

Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.

MAGI-2-preview

Python

82

MAGI-2-preview: Scaling Video Generation Models Efficiently

Audio8_TTS

Python

82

SOTA-Class TTS at Compact Scale

PixelRAG

Python

95

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

gorest-2d-animation-spritesheet-generator

TypeScript

90

Codex-assisted local 2D animation spritesheet generator and scene compositing workspace.

lottie

TypeScript

80

Generate production-ready Lottie animations with Claude Code or Codex

Audar-ASR-V1

Python

68

Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.

RaptorQR

TypeScript

72

Ultra-fast offline file and text transfer over animated QR codes with WASM fast_qr, ZXing and RaptorQ.

MoneyPrinterTurbo

Python

100

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

stickman-video-director

Shell

77

Turn copy into rich one-minute Gemini Omni Flash stickman video prompt packages.

functional-skill-creator

JavaScript

72

fskill-creator turns your long-text SKILL into functions, making it modular, testable and trackable for better long-term maintenance and iteration

hayamimi

Python

72

早耳 - Real-time multilingual speech-to-text on CPU only. Live subtitles, browser dashboard, speaker labels, translation. No GPU, no cloud.

latticedb

Zig

82

Embedded single-file knowledge graph database with vector search and full-text search for AI/RAG apps

humanizer-stack

Python

72

Two-pass pipeline for removing AI writing tells from outward-facing text: a surface pass plus a structural pass grounded in the StoryScope study. Packaged as Claude Code Skills. Free community: skool.com/jens-ai-community-1306

diction

Go

77

Diction is Open Source self-hosted alternative to WisprFlow - iOS speech-to-text keyboard

transformers

Python

95

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

karakeep

TypeScript

95

A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search

Crisp

Swift

87

Free, open-source external monitor control for macOS: a lightweight menu bar app with sharp HiDPI/Retina scaling (no more blurry or tiny text), DDC brightness, presets, and virtual displays. A free alternative to BetterDisplay and Lunar, including features they charge for.

ai-copywriter

Python

77

An AI copywriter that uses real copywriting skills + real marketing knowledge with human tone.

kimodo.cpp

C++

72

Animate skeletons with natural language; NVIDIA's Kimodo ported to C++/GGML

eidos

Rust

63

Private, intelligent search across every machine you own. Systems remain searchable when offline, including files buried inside VMs and archives.

best-humanizer-handbook

53

Best AI Humanizer Handbook A practical guide to making AI-assisted writing clearer, more credible, and more human

Lexicon

JavaScript

72

The free open source offline writing assistant assist with grammar, rewriting & tone entirely on your machine.

Wake

Rust

82

All your AI agent sessions in one place — browse, search, resume. Rust + GPUI.

yap

Swift

77

Free, open source voice dictation for macOS. On-device transcription with Apple's Speech framework. No cloud/no API keys/no account.

system-atlas

HTML

77

An agent skill that turns an architecture discussion into an explorable isometric atlas: one data file, an interactive map and a generated SYSTEM.md

neovim

Vim Script

95

Vim-fork focused on extensibility and usability

papra

TypeScript

90

The minimalistic document archiving platform.

ocr-it

JavaScript

77

Chrome extension: pin a screen region once, then hotkey your way through a paginated document. OCR runs 100% offline via bundled Tesseract.

qwen-scribe

Python

73

Private, local transcription and system-wide dictation for Apple Silicon.

sloptrim

Python

77

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

jarvis

Shell

68

Jarvis meta-repository: shared docs, configs, and setup scripts

rescript

TypeScript

82

🎬 Open source, transcript-based video/audio editor that lives in the browser.

kimi-k3-mlx

Python

62

MLX port of moonshotai/Kimi-K3 (2.78T multimodal MoE): streaming converter, REAP expert pruning, and per-language expert-overlap analysis

rootprint

TypeScript

63

Open-source, self-hosted log management platform built with Hono, SvelteKit and Quickwit!

better-voice

Swift

82

Voice dictation with the screen context you point at.

ssh-clipboard

Rust

68

Native encrypted clipboard sync over SSH for macOS and Linux

ambient-context

Rust

73

A menu bar app that keeps a written record of what you worked on.

Noustiny

TypeScript

54

An agent native video creation pipeline that runs on top of Hermes Agent